{"id":"https://openalex.org/W4412886676","doi":"https://doi.org/10.18653/v1/2025.acl-long.222","title":"Sharper and Faster mean Better: Towards More Efficient Vision-Language Model for Hour-scale Long Video Understanding","display_name":"Sharper and Faster mean Better: Towards More Efficient Vision-Language Model for Hour-scale Long Video Understanding","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412886676","doi":"https://doi.org/10.18653/v1/2025.acl-long.222"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.222","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.222","pdf_url":"https://aclanthology.org/2025.acl-long.222.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.222.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063777354","display_name":"Daoze Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daoze Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108984539","display_name":"Yuze Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuze Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026348811","display_name":"Jintao Huang","orcid":"https://orcid.org/0000-0003-3703-0468"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jintao Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5104162468","display_name":"Yingda Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yingda Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9349,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.77166326,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4423","last_page":"4439"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9901999831199646,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7242911458015442},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.6098294258117676},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4278649687767029},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.409257709980011},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09319829940795898},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.08770909905433655}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7242911458015442},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6098294258117676},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4278649687767029},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.409257709980011},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09319829940795898},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.08770909905433655}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.222","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.222","pdf_url":"https://aclanthology.org/2025.acl-long.222.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.222","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.222","pdf_url":"https://aclanthology.org/2025.acl-long.222.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412886676.pdf","grobid_xml":"https://content.openalex.org/works/W4412886676.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Despite":[0],"existing":[1,126],"multimodal":[2],"language":[3,21],"models":[4],"showing":[5],"impressive":[6],"performance":[7,123],"on":[8,73],"the":[9,74,78,89,107,115],"video":[10,42,94,127,135],"understanding":[11,128,136],"task,":[12],"extremely":[13],"long":[14,41,49,61,134],"videos":[15,62],"still":[16],"pose":[17],"significant":[18],"challenges":[19],"to":[20,67,77,86,125],"model's":[22],"context":[23],"length,":[24],"memory":[25,141],"consumption,":[26],"and":[27,71,100,140,145],"computational":[28],"complexity.To":[29],"address":[30],"these":[31],"issues,":[32],"we":[33,51,80],"propose":[34],"a":[35,53,82,98],"vision-language":[36],"model":[37,88,143],"named":[38],"Sophia":[39,120],"for":[40,133],"understanding,":[43],"which":[44,58,96],"can":[45],"efficiently":[46],"handle":[47],"hour-scale":[48],"videos.First,":[50],"employ":[52],"Shot-adaptive":[54],"Frame":[55],"Pruning":[56],"technique,":[57],"naturally":[59],"segments":[60],"into":[63],"multiple":[64],"camera":[65],"shots,":[66],"more":[68],"sharply":[69],"identify":[70],"focus":[72],"frames":[75],"relevant":[76],"query.Additionally,":[79],"introduce":[81],"Hierarchical":[83],"Attention":[84],"mechanism":[85],"effectively":[87],"long-term":[90],"temporal":[91],"dependencies":[92],"between":[93],"frames,":[95],"achieves":[97],"time":[99,139],"space":[101],"complexity":[102],"of":[103],"O(N":[104],")":[105],"w.r.t.":[106],"input":[108],"sequence":[109],"length":[110],"N":[111],"while":[112],"theoretically":[113],"maintaining":[114],"global":[116],"modeling":[117],"efficiency.Experimentally,":[118],"our":[119],"exhibits":[121],"competitive":[122],"compared":[124],"baselines":[129],"across":[130],"various":[131],"benchmarks":[132],"with":[137],"reduced":[138],"consumption.The":[142],"code":[144],"weights":[146],"are":[147],"available":[148],"at":[149],"this":[150],"repository.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}